|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"eval_steps": 500, |
|
"global_step": 990, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.06060606060606061, |
|
"grad_norm": 0.42527449131011963, |
|
"learning_rate": 5.05050505050505e-07, |
|
"loss": 1.3881, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.12121212121212122, |
|
"grad_norm": 0.4301815330982208, |
|
"learning_rate": 1.01010101010101e-06, |
|
"loss": 1.4123, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.18181818181818182, |
|
"grad_norm": 0.44010022282600403, |
|
"learning_rate": 1.5151515151515152e-06, |
|
"loss": 1.3928, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.24242424242424243, |
|
"grad_norm": 0.4670265018939972, |
|
"learning_rate": 2.02020202020202e-06, |
|
"loss": 1.3912, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.30303030303030304, |
|
"grad_norm": 0.4875299632549286, |
|
"learning_rate": 2.5252525252525258e-06, |
|
"loss": 1.3781, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.36363636363636365, |
|
"grad_norm": 0.37787771224975586, |
|
"learning_rate": 3.0303030303030305e-06, |
|
"loss": 1.3347, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.42424242424242425, |
|
"grad_norm": 0.370220810174942, |
|
"learning_rate": 3.5353535353535356e-06, |
|
"loss": 1.303, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.48484848484848486, |
|
"grad_norm": 0.3872508406639099, |
|
"learning_rate": 4.04040404040404e-06, |
|
"loss": 1.2378, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.5454545454545454, |
|
"grad_norm": 0.4406280815601349, |
|
"learning_rate": 4.5454545454545455e-06, |
|
"loss": 1.1575, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.6060606060606061, |
|
"grad_norm": 0.5964057445526123, |
|
"learning_rate": 4.999921328558333e-06, |
|
"loss": 1.0205, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.6666666666666666, |
|
"grad_norm": 0.51554936170578, |
|
"learning_rate": 4.990486745229364e-06, |
|
"loss": 0.8522, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.7272727272727273, |
|
"grad_norm": 0.5323845148086548, |
|
"learning_rate": 4.965385884295467e-06, |
|
"loss": 0.7621, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.7878787878787878, |
|
"grad_norm": 0.4954449236392975, |
|
"learning_rate": 4.924776641419513e-06, |
|
"loss": 0.6637, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.8484848484848485, |
|
"grad_norm": 0.7475800514221191, |
|
"learning_rate": 4.868914466936038e-06, |
|
"loss": 0.6373, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.9090909090909091, |
|
"grad_norm": 0.4374482333660126, |
|
"learning_rate": 4.798150758954164e-06, |
|
"loss": 0.6296, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.9696969696969697, |
|
"grad_norm": 0.47152256965637207, |
|
"learning_rate": 4.7129306529060415e-06, |
|
"loss": 0.5948, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.0303030303030303, |
|
"grad_norm": 0.5148698687553406, |
|
"learning_rate": 4.613790221445511e-06, |
|
"loss": 0.5775, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.0909090909090908, |
|
"grad_norm": 0.375209778547287, |
|
"learning_rate": 4.501353102310901e-06, |
|
"loss": 0.5469, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.1515151515151516, |
|
"grad_norm": 0.4789840877056122, |
|
"learning_rate": 4.376326575364206e-06, |
|
"loss": 0.5645, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.2121212121212122, |
|
"grad_norm": 0.5624423027038574, |
|
"learning_rate": 4.239497113483819e-06, |
|
"loss": 0.5436, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.2727272727272727, |
|
"grad_norm": 0.46569859981536865, |
|
"learning_rate": 4.091725435297721e-06, |
|
"loss": 0.548, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.3333333333333333, |
|
"grad_norm": 0.44934600591659546, |
|
"learning_rate": 3.933941090877615e-06, |
|
"loss": 0.5509, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.393939393939394, |
|
"grad_norm": 0.41648173332214355, |
|
"learning_rate": 3.767136614452458e-06, |
|
"loss": 0.528, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 1.4545454545454546, |
|
"grad_norm": 0.5370034575462341, |
|
"learning_rate": 3.5923612809233987e-06, |
|
"loss": 0.5338, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 1.5151515151515151, |
|
"grad_norm": 0.4544106125831604, |
|
"learning_rate": 3.410714505454486e-06, |
|
"loss": 0.543, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.5757575757575757, |
|
"grad_norm": 0.4658797085285187, |
|
"learning_rate": 3.2233389276586325e-06, |
|
"loss": 0.522, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 1.6363636363636362, |
|
"grad_norm": 0.4451984465122223, |
|
"learning_rate": 3.0314132238824416e-06, |
|
"loss": 0.5223, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 1.696969696969697, |
|
"grad_norm": 0.43969258666038513, |
|
"learning_rate": 2.8361446928038298e-06, |
|
"loss": 0.5184, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 1.7575757575757576, |
|
"grad_norm": 0.4263152778148651, |
|
"learning_rate": 2.6387616609823506e-06, |
|
"loss": 0.5223, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 1.8181818181818183, |
|
"grad_norm": 0.4743904769420624, |
|
"learning_rate": 2.440505756134732e-06, |
|
"loss": 0.5376, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 1.878787878787879, |
|
"grad_norm": 0.45021238923072815, |
|
"learning_rate": 2.242624096740164e-06, |
|
"loss": 0.5187, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 1.9393939393939394, |
|
"grad_norm": 0.45092540979385376, |
|
"learning_rate": 2.046361447106244e-06, |
|
"loss": 0.5207, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"grad_norm": 0.4477311372756958, |
|
"learning_rate": 1.852952387243698e-06, |
|
"loss": 0.5171, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 2.0606060606060606, |
|
"grad_norm": 0.41556811332702637, |
|
"learning_rate": 1.6636135468049122e-06, |
|
"loss": 0.5086, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 2.121212121212121, |
|
"grad_norm": 0.4341486990451813, |
|
"learning_rate": 1.479535951938243e-06, |
|
"loss": 0.5067, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 2.1818181818181817, |
|
"grad_norm": 0.4101578891277313, |
|
"learning_rate": 1.301877533199859e-06, |
|
"loss": 0.5119, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 2.242424242424242, |
|
"grad_norm": 0.43040916323661804, |
|
"learning_rate": 1.1317558416516696e-06, |
|
"loss": 0.5132, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 2.303030303030303, |
|
"grad_norm": 0.4996863901615143, |
|
"learning_rate": 9.702410189643838e-07, |
|
"loss": 0.5038, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 2.3636363636363638, |
|
"grad_norm": 0.5682224035263062, |
|
"learning_rate": 8.183490657468687e-07, |
|
"loss": 0.5146, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 2.4242424242424243, |
|
"grad_norm": 0.5291648507118225, |
|
"learning_rate": 6.770354504470575e-07, |
|
"loss": 0.4873, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 2.484848484848485, |
|
"grad_norm": 0.4898635149002075, |
|
"learning_rate": 5.471890990272666e-07, |
|
"loss": 0.5072, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 2.5454545454545454, |
|
"grad_norm": 0.4250613749027252, |
|
"learning_rate": 4.2962680322157335e-07, |
|
"loss": 0.5074, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 2.606060606060606, |
|
"grad_norm": 0.5462311506271362, |
|
"learning_rate": 3.250880825498026e-07, |
|
"loss": 0.5058, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 2.6666666666666665, |
|
"grad_norm": 0.4744057059288025, |
|
"learning_rate": 2.3423053240837518e-07, |
|
"loss": 0.5264, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 2.7272727272727275, |
|
"grad_norm": 0.4270976781845093, |
|
"learning_rate": 1.5762568750059604e-07, |
|
"loss": 0.5156, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 2.787878787878788, |
|
"grad_norm": 0.5914854407310486, |
|
"learning_rate": 9.575542662726756e-08, |
|
"loss": 0.4896, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 2.8484848484848486, |
|
"grad_norm": 0.4599030315876007, |
|
"learning_rate": 4.9008941453107527e-08, |
|
"loss": 0.5131, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 2.909090909090909, |
|
"grad_norm": 0.5342442989349365, |
|
"learning_rate": 1.768028831677926e-08, |
|
"loss": 0.5163, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 2.9696969696969697, |
|
"grad_norm": 0.4838986098766327, |
|
"learning_rate": 1.9665384847583622e-09, |
|
"loss": 0.5083, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 990, |
|
"total_flos": 4.559176483209216e+16, |
|
"train_loss": 0.70023385491034, |
|
"train_runtime": 1270.7835, |
|
"train_samples_per_second": 3.116, |
|
"train_steps_per_second": 0.779 |
|
} |
|
], |
|
"logging_steps": 20, |
|
"max_steps": 990, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4.559176483209216e+16, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|